> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-comfy-docs-comfyapi-search.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# EmptyHiDreamO1LatentImage - ComfyUI Built-in Node Documentation

> This node creates an empty latent image in pixel space for the HiDream-O1-Image model.

This node creates an empty latent image in pixel space for the HiDream-O1-Image model. It generates a blank tensor of zeros that acts as the starting point for image generation, with dimensions defined by the width, height, and batch size inputs.

## Inputs

| Parameter    | Description                                                                                                                                                                                | Data Type | Required | Range                 |
| ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------- | -------- | --------------------- |
| `width`      | The width of the latent image in pixels. Default: 2048. The value must be a multiple of 32. The model was trained at about 4 megapixels; lower resolutions may reduce quality noticeably.  | INT       | Yes      | 64 to 4096 (step: 32) |
| `height`     | The height of the latent image in pixels. Default: 2048. The value must be a multiple of 32. The model was trained at about 4 megapixels; lower resolutions may reduce quality noticeably. | INT       | Yes      | 64 to 4096 (step: 32) |
| `batch_size` | The number of latent images to generate in a single batch. Default: 1.                                                                                                                     | INT       | Yes      | 1 to 64               |

## Outputs

| Output Name | Description                                                                                                 | Data Type |
| ----------- | ----------------------------------------------------------------------------------------------------------- | --------- |
| `samples`   | A tensor filled with zeros representing the empty latent image, with shape (batch\_size, 3, height, width). | LATENT    |

## Notes

* The HiDream-O1-Image model was trained at approximately 4 megapixels. Using significantly lower resolutions may result in noticeably reduced image quality.
* Trained resolutions include: 2048x2048, 2304x1728, 1728x2304, 2560x1440, 1440x2560, 2496x1664, 1664x2496, 3104x1312, 1312x3104, 2304x1792, 1792x2304.

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyHiDreamO1LatentImage/en.md)

***

**Source fingerprint (SHA-256):** `7412639e261512d9174e60009143c8c06c354e2a20ada7271837d72053426be5`